Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality trade-off. For one thing, fully NAT models with efficient inference perform inferior to their autoregressive counterparts. For another, iterative NAT models can, though, achieve comparable performance while diminishing the advantage of speed. In this paper, we propose RenewNAT, a flexible framework with high efficiency and effectiveness, to incorporate the merits of fully and iterative NAT models. RenewNAT first generates the potential translation results and then renews them in a single pass. It can achieve significant performance improvements at the same expense as traditional NAT models (without introducing additional model parameters and decoding latency). Experimental results on various translation benchmarks (e.g., \textbf{4} WMT) show that our framework consistently improves the performance of strong fully NAT methods (e.g., GLAT and DSLP) without additional speed overhead.
翻译:提议采用非潜移式神经机器翻译模型,以加快推论过程,同时保持较高的性能;然而,现有的NAT模型难以实现预期的效率质量权衡。一方面,具有有效推论的完全NAT模型比自动递进模型低;另一方面,迭代NAT模型可以取得可比较的性能,同时降低速度的优势。在本文件中,我们提议采用具有高效率和效力的灵活框架,即FirstNAT,以充分、迭代NAT模型的优点。ServerNAT首先产生潜在的翻译结果,然后在单一通道上更新这些结果。它可以以与传统的NAT模型相同的费用(不采用额外的模型参数和分解拉长)实现显著的性能改进。关于各种翻译基准的实验结果(例如,\ textbf{4}WMT)表明,我们的框架在不增加速度管理的情况下不断改进强型NAT方法(例如,GLT和DSLP)的性能。</s>